[Cherry-pick] [AMD][GLUON] Support scalar other value for loads (#8039) (#640)

Summary:
Cherry-picked from upstream OAI repository.

Original Commit: f804bbc
Original Author: Pengzhan Zhao
Original Date: 2025-09-02 14:23:38 -0700

Original commit message:
```
[AMD][GLUON] Support scalar other value for loads (#8039)

Support scalar other value for following ops:

- `amd.cdna3.buffer_load`
- `amd.cdna4.async_copy.buffer_load_to_shared`
- `amd.cdna4.async_copy.global_load_to_shared`

We will explicitly convert scalar other to a tensor and cast to match
the pointer type.
```

This PR was automatically cherry-picked from the upstream triton-lang/triton repository.

Pull Request resolved: #640

Reviewed By: njriasan

Differential Revision: D86329168

Pulled By: agron911

fbshipit-source-id: 28651948f14794c7df9cd3755398f4195921f466

Author: borontion